Predictive maintenance
Finding the 22% of chargers behind 69% of failures
A European charge point operator fixed chargers after they failed. R-One showed where failures concentrate, and which 40% of the estate could safely wait.
- Client
- European charge point operator
- Region
- Europe
- Estate
- AC and DC chargers
69%
of failures came from the 22% of chargers R-One ranked highest for the next 7 days
2%
of failures came from the 40% ranked lowest, which can be deprioritised
3–11x
more likely to hit a real failure than picking chargers at random
The challenge
The operator ran a mixed AC and DC estate and maintained it fix-on-fail. Every failure reached a driver before it reached a technician.
Downtime was uneven. DC chargers were down 12% of the time, against 1.5% for AC.
Not every problem showed. A charger can report Available while sessions quietly fail to start, so some of the faults that mattered never reached a failure list.
A charger counted as down when its status was unknown or out of order.
What R-One did
Read the operating record
R-One worked from data the operator already had: charger status and fault history, usage and maintenance records. There was nothing new to install.
Surface the invisible faults
Quiet problems that never cause an outage on their own, but wear a charger down, were flagged separately from the alarms the CMS already raises.
Score every charger on two horizons
Each charger got a failure risk for the next 7 days and for the next 21 days, sorted into five tiers from very high to very low.
Test it on data the model had not seen
The model learned from most of the history and was scored on a held-out part it had never seen, so the results reflect what it would have said in advance.
What it found
Ranked by risk for the next 7 days, the top 22% of chargers accounted for 69% of failures. Over the longer 21-day view, the same share still held 62%.
Failures concentrate in a few chargers
- Very high risk2% of chargers, 19% of failures.
- High risk20% of chargers, 50% of failures.
- Medium risk20% of chargers, 20% of failures.
- Low risk18% of chargers, 10% of failures.
- Very low risk40% of chargers, 2% of failures.
Far better than picking at random
- Picking chargers at random6%
- R-One’s highest-risk tiers18% to 67%
4 in 10
hours of downtime tied to invisible faults
R-One’s invisible-fault engine had detected the underlying problem behind roughly four in ten hours of downtime. On DC chargers, 78% of its alerts lined up with real downtime.
What this changes
Send technicians where failures concentrate
A ranked list turns a network-wide problem into a short, ordered work list.
Stop spending visits on the quietest chargers
The lowest-risk 40% of chargers produced 2% of failures, so routine attention can move elsewhere.
Act before the driver notices
A forecast arrives ahead of the failure. Fix-on-fail arrives after it.
These results are a back-test on the operator’s own history: R-One scored data it had not been trained on, and the outcomes were checked against what actually happened.
See what R-One finds in your network.
Share your charger history and we will show you your own risk ranking.